CN112465109A - Green house controlling means based on cloud limit is in coordination - Google Patents
Green house controlling means based on cloud limit is in coordination Download PDFInfo
- Publication number
- CN112465109A CN112465109A CN202011275023.5A CN202011275023A CN112465109A CN 112465109 A CN112465109 A CN 112465109A CN 202011275023 A CN202011275023 A CN 202011275023A CN 112465109 A CN112465109 A CN 112465109A
- Authority
- CN
- China
- Prior art keywords
- data
- agricultural greenhouse
- cloud
- growth process
- crop growth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000012010 growth Effects 0.000 claims abstract description 103
- 238000000034 method Methods 0.000 claims abstract description 91
- 230000008569 process Effects 0.000 claims abstract description 82
- 238000011217 control strategy Methods 0.000 claims abstract description 69
- 238000007726 management method Methods 0.000 claims abstract description 35
- 230000005540 biological transmission Effects 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000013480 data collection Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims description 29
- 238000013500 data storage Methods 0.000 claims description 24
- 239000002689 soil Substances 0.000 claims description 16
- 241000607479 Yersinia pestis Species 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 201000010099 disease Diseases 0.000 claims description 12
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 7
- 238000012098 association analyses Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 8
- 235000013311 vegetables Nutrition 0.000 description 6
- 241000238631 Hexapoda Species 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000010219 correlation analysis Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000035784 germination Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 235000003095 Vaccinium corymbosum Nutrition 0.000 description 2
- 240000000851 Vaccinium corymbosum Species 0.000 description 2
- 235000017537 Vaccinium myrtillus Nutrition 0.000 description 2
- 235000021014 blueberries Nutrition 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 240000009088 Fragaria x ananassa Species 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 235000021012 strawberries Nutrition 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Animal Husbandry (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Biodiversity & Conservation Biology (AREA)
- Agronomy & Crop Science (AREA)
- Game Theory and Decision Science (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Automation & Control Theory (AREA)
- Greenhouses (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an agricultural greenhouse control device based on cloud edge coordination, wherein a data acquisition unit acquires agricultural greenhouse crop growth process data; the data transmission unit sends the crop growth process data collected by the data collection unit to the edge calculation unit; the edge calculation unit is arranged on the local control computer, receives the crop growth process data sent by the data transmission unit, generates a log file of the crop growth process, and locally controls the agricultural greenhouse; the cloud computing unit runs on the cloud server, stores and processes crop growth process data, and constructs an agricultural greenhouse control strategy model. The agricultural greenhouse control device based on cloud edge coordination has the technical advantages that the problems of insufficient data association analysis and insufficient sharing in the crop growth process can be solved, crop growth environment and state information can be comprehensively given, efficient and accurate intelligent remote management of an agricultural greenhouse is realized, and the like.
Description
Technical Field
The invention relates to the field of crop cultivation, in particular to an agricultural greenhouse control device based on cloud edge cooperation.
Background
China is the earliest country of greenhouse cultivation origin. It has been possible to cultivate a wide variety of vegetables in protective facilities (greenhouses) well before 2000 years. In the 60 s of the 20 th century, the construction and development of plastic greenhouses began in China. With the continuous development of agriculture in China, the planting area of greenhouses and greenhouse vegetables is increased year after year, and the greenhouse has the functions of changing the growth environment of plants, avoiding the adverse effects of external four-season changes and severe weather on the growth of crops and creating proper good conditions for the growth of plants. When the greenhouse is used for planting vegetables, if the temperature and the humidity in the greenhouse are not suitable, the vegetables can grow badly. When the illumination is sufficient in the daytime, the temperature in the greenhouse rises, and if the greenhouse cannot be ventilated and cooled in time, the growth of vegetables is seriously influenced, and even the infection and the occurrence of vegetable diseases and insect pests are caused.
The current automatic control system of the agricultural greenhouse generally adopts the traditional industrial control scheme, and the field comprises three main parts, namely a sensor, a control cabinet, namely a controller and an actuator. Greenhouse managers want to know the information such as the temperature and humidity of air in the greenhouse, illumination, the temperature and humidity of soil and the like, and must look over sensors such as a thermometer, a humidity display instrument, illumination detection equipment and the like in the greenhouse in person to obtain the growth environment information of crops in the current greenhouse, and artificially adjust the growth environment of the crops through a control cabinet, so that the production efficiency is low, the intelligent degree is low, and a large amount of manpower and material resources are wasted. In order to meet the requirements of normal growth, economic investment and the like of agricultural greenhouse crops, the agricultural greenhouse is operated in a low-cost mode, and the agricultural greenhouse needs to be remotely, real-timely and intelligently controlled.
Chinese utility model patent CN201420576405.5 gathers the environmental parameter in the big-arch shelter through adjusting wireless sensing unit to with wireless connection between each module in the big-arch shelter, only realized the inside environment of remote control green house. The chinese invention patent CN201710873304.2, through the cloud server, collects and stores the parameters of each sensor, senses the field environment, and although the results can be given and wirelessly sent to the corresponding facility cultivation device for execution according to the predetermined and controlled strategy and the opinions provided by the expert database, the parameter control of each sensor is independent from each other, and the internal relationship between them is not considered as a whole. These prior art, though solved the long-range, intelligent control problem of green house to a certain extent. However, the collected data does not include crop image data, the control strategy is simple, and most of the collected data is analyzed by using a centralized cloud platform directly, which causes large bandwidth occupation and network delay, and particularly, a large amount of 'garbage' data does not need to be transmitted to the cloud end, thereby causing resource waste and being difficult to control the agricultural greenhouse in real time.
Disclosure of Invention
The invention aims to provide an agricultural greenhouse control device based on cloud edge coordination, so as to give crop growth environment and state information more comprehensively and realize efficient and accurate intelligent remote management on an agricultural greenhouse.
In order to solve the technical problems, the invention adopts the following technical scheme.
An agricultural greenhouse control device based on cloud edge coordination is characterized by comprising a data acquisition unit, a data transmission unit, an edge computing unit and a cloud computing unit;
the data acquisition unit is used for acquiring growth process data of agricultural greenhouse crops;
the data transmission unit is used for sending the crop growth process data collected by the data collection unit to the edge calculation unit;
the edge calculation unit is arranged on the local control computer and used for receiving the crop growth process data sent by the data transmission unit, generating a log file of the crop growth process according to the crop growth process data and simultaneously carrying out local control on the agricultural greenhouse;
the cloud computing unit runs on the cloud server and is used for storing and processing crop growth process data and building an agricultural greenhouse control strategy model based on deep learning and expert knowledge.
The agricultural greenhouse control device based on cloud edge coordination also has the following characteristics.
The edge computing unit comprises a local data storage module, a local data preprocessing module, a local control strategy management module, a local control strategy operation module and a local early warning management module.
The cloud computing unit comprises a remote data storage module, a remote data analysis module, a remote control strategy management module and a remote control strategy operation module.
The crop growth process data comprises soil pH value, soil EC value, CO2 concentration value, soil temperature and humidity, light intensity, air temperature and humidity, insect pest data and disease data.
The pest data and the disease data comprise crop video data and crop image data collected by a camera device, and the crop video data and the crop image data are processed through a deep learning algorithm to identify the growth period and the pest of crops.
The local data storage module is used for storing crop growth process data in a current period of time and uploading the data to the cloud computing unit when a task is idle.
The local data preprocessing module is used for carrying out uniform alignment and data preprocessing on the time stamps of the crop growth process data in the local data storage module, and transmitting the data characteristics extracted after preprocessing to the cloud computing unit through the data transmission unit.
And the local control strategy management module is used for requesting the latest trained agricultural greenhouse control strategy model, the data preprocessing rule and the feature extraction rule from the cloud computing unit.
And the remote data analysis module is used for training the agricultural greenhouse control strategy model by using the data stored by the remote data storage module.
And the remote control strategy management module is used for updating and controlling the agricultural greenhouse control strategy model, receiving and processing the agricultural greenhouse control strategy model from the local control strategy management module and the data preprocessing rule and feature extraction rule requests.
The invention has the beneficial effects that:
the invention discloses an agricultural greenhouse control device based on cloud-edge cooperation, which comprises a data acquisition unit, a data transmission unit, an edge computing unit and a cloud computing unit; the data acquisition unit is used for acquiring growth process data of agricultural greenhouse crops; the data transmission unit is used for sending the crop growth process data collected by the data collection unit to the edge calculation unit; the edge calculation unit is arranged on the local control computer and used for receiving the crop growth process data sent by the data transmission unit, generating a log file of the crop growth process according to the crop growth process data and simultaneously carrying out local control on the agricultural greenhouse; the cloud computing unit runs on the cloud server and is used for storing and processing crop growth process data and building an agricultural greenhouse control strategy model based on deep learning and expert knowledge.
(1) Real-time monitoring and intelligent control of bottom equipment of the agricultural greenhouse are realized by utilizing a cloud edge cooperative framework; through continuous innovation of three aspects of crop visual image acquisition, crop growth process data integral analysis and edge control, the agricultural greenhouse management personnel can be helped to collect and manage abundant data, and the flexibility of agricultural greenhouse management is realized.
(2) By adopting a data processing mode combining real-time response of the edge computing unit and deep analysis of the cloud computing unit, on one hand, the PLC device which can be correspondingly installed and connected in the environment of the edge computing unit in real time can send data and process the sent data in time, and the delay is almost zero, on the other hand, the cloud computing unit collects the data and then conducts deep analysis and edge computing, so as to guide the edge computing to correctly respond to the PLC device to control bottom equipment. Meanwhile, the uploading time of mass data is shortened, network resources are saved, the problems of insufficient data correlation analysis and insufficient sharing in the crop growth process are solved, the storage cost on the cloud can be obviously reduced, and effective data management is facilitated.
According to the agricultural greenhouse control device based on cloud-edge cooperation, the cloud computing unit carries out deep analysis after collecting data of the edge computing unit and feeds back the data to the edge computing unit, and the agricultural greenhouse control device has the technical advantages that the problems of insufficient correlation analysis and insufficient sharing of crop growth process data can be solved, crop growth environment and state information can be comprehensively given, efficient and accurate intelligent remote management of an agricultural greenhouse is achieved, and the like.
Drawings
Fig. 1 is a block diagram of an agricultural greenhouse control device based on cloud edge coordination.
Fig. 2 is a flow chart of agricultural greenhouse control strategy model training of a remote data analysis module of an agricultural greenhouse control device based on cloud edge coordination.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
As shown in fig. 1, an agricultural greenhouse control device based on cloud-edge coordination includes a data acquisition unit, a data transmission unit, an edge computing unit and a cloud computing unit;
the data acquisition unit is used for acquiring growth process data of agricultural greenhouse crops;
the data transmission unit is used for sending the crop growth process data collected by the data collection unit to the edge calculation unit;
the edge calculation unit is arranged on the local control computer and used for receiving the crop growth process data sent by the data transmission unit, generating a log file of the crop growth process according to the crop growth process data and simultaneously carrying out local control on the agricultural greenhouse;
the cloud computing unit runs on the cloud server and is used for storing and processing crop growth process data and building an agricultural greenhouse control strategy model based on deep learning and expert knowledge.
The edge computing unit comprises a local data storage module, a local data preprocessing module, a local control strategy management module, a local control strategy operation module and a local early warning management module.
The cloud computing unit comprises a remote data storage module, a remote data analysis module, a remote control strategy management module and a remote control strategy operation module.
The crop growth process data comprises soil pH value, soil EC value, CO2 concentration value, soil temperature and humidity, light intensity, air temperature and humidity, insect pest data and disease data.
The pest data and the disease data comprise crop video data and crop image data collected by a camera device, and the crop video data and the crop image data are processed through a deep learning algorithm to identify the growth period and the pest of crops.
The local data storage module is used for storing crop growth process data in a current period of time and uploading the data to the cloud computing unit when a task is idle.
The local data preprocessing module is used for carrying out uniform alignment and data preprocessing on the time stamps of the crop growth process data in the local data storage module, and transmitting the data characteristics extracted after preprocessing to the cloud computing unit through the data transmission unit.
And the local control strategy management module is used for requesting the latest trained agricultural greenhouse control strategy model, the data preprocessing rule and the feature extraction rule from the cloud computing unit.
And the remote data analysis module is used for training the agricultural greenhouse control strategy model by using the data stored by the remote data storage module.
And the remote control strategy management module is used for updating and controlling the agricultural greenhouse control strategy model, receiving and processing the agricultural greenhouse control strategy model from the local control strategy management module and the data preprocessing rule and feature extraction rule requests.
The invention discloses an agricultural greenhouse control device based on cloud edge coordination, which comprises: the device comprises a data acquisition unit, an edge computing unit, a cloud computing unit and a data transmission unit. On the basis of the prior art, the method increases the collection of crop image information, performs data fusion on sensor data at the edge side to share the pressure of cloud computing, relieves the high delay, high energy consumption and low bandwidth utilization rate caused by cloud computing and edge computing isolation or incompatibility by means of a cloud-edge cooperation method, provides crop growth environment and state information more comprehensively, and performs dynamic real-time control arrangement on the agricultural greenhouse more quickly on the basis to realize efficient and accurate intelligent remote management on the agricultural greenhouse.
The data acquisition unit is used for acquiring crop growth process data of the agricultural greenhouse and transmitting the acquired data to the edge calculation unit at fixed time intervals through the data transmission unit.
Further, the crop growth process data comprises: soil pH value, soil EC value, CO2 concentration value, soil humiture, light intensity, air humiture, insect pest data, disease data and the like.
Furthermore, the fixed time intervals can be set according to different types of the data of the crop growth process.
Preferably, the pest and disease data can be obtained by a camera, a robot/unmanned aerial vehicle carrying an image sensor, and a smart phone/tablet collecting crop visual pictures, and the crop growth period identification and pest and disease identification are carried out through a deep learning algorithm.
The edge computing unit runs at a local computer terminal and is used for carrying out data fusion on the collected crop growth process data locally to generate a log file of the crop growth process and simultaneously carrying out local control on the agricultural greenhouse.
The edge calculation unit includes: the system comprises a local data storage module, a local data preprocessing module, a local control strategy management module, a local control strategy operation module and a local early warning management module.
Further, the local data storage module is used for storing crop growth process data in a current period of time and uploading the data to the cloud computing unit when a task is idle.
Preferably, the task is idle, which means that the task does not affect the data processing and analyzing task currently running on the edge computing unit and the cloud computing unit.
Further, the local data preprocessing module is used for performing uniform alignment of time stamps and data preprocessing on the crop growth process data in the local data storage module, and transmitting the data characteristics extracted after preprocessing to the cloud computing unit through the data transmission unit;
preferably, the data preprocessing adopts different data preprocessing rules and feature extraction rules according to different data types of the crop growth process.
Specifically, the data preprocessing rule includes a large amount of environmental noise contained in the acquired data, and a plurality of abnormal data are generated. In the data processing process, denoising by adopting a finite amplitude filtering method, a median value filtering method, an arithmetic mean filtering method or a wavelet threshold value filtering method; formatting treatment is carried out on unformatted data including pictures, the pictures after conversion are verified, and an image processing algorithm is used, such as: coordinate transformation, image graying, image enhancement, image filtering and image segmentation, and then analyzing, processing and identifying the detection target characteristics.
Specifically, the feature extraction rules include data extraction modes, classified feature attributes, selected feature transformation and selection algorithms, and deep learning models.
Further, the local control strategy management module is used for requesting the latest trained agricultural greenhouse control strategy model, the data preprocessing rule and the feature extraction rule from the cloud computing unit, and the request frequency can be set according to the requirements.
Furthermore, the local control strategy operation module analyzes the result of the real-time data analysis of the crop growth process according to the local data preprocessing module. And when the cloud computing unit cannot be connected, operating the current agricultural greenhouse control strategy model in the local control strategy management module, and issuing the equipment set value obtained by operation in the crop growth process to the PLC device through the data transmission unit to control the bottom equipment. The bottom layer equipment comprises an execution device and a collection device.
Preferably, the device setting value can be updated online when the device setting value is connected with the cloud computing unit, the device setting value is automatically switched to an updated value, and the updated value is obtained by the local control strategy operation module according to the latest trained agricultural greenhouse control strategy model.
Preferably, the executing device of the bottom layer device is a device capable of adjusting the crop growth process data, and includes: the device comprises an inner sun-shading device, a top window opening device, an outer window opening device, an axial flow fan, a circulating fan, a wet curtain water pump and an ozone prevention and control device.
Preferably, the acquisition device of the bottom layer device further comprises a camera for shooting monitoring images and recording monitoring videos, in addition to the sensor for monitoring parameters such as temperature and humidity. By adjusting the parameters of the camera, better crop growth period and better pest and disease identification effect are obtained.
And further, the local early warning management module is used for giving an alarm when the current working state of the bottom layer equipment cannot be adjusted according to the agricultural greenhouse control strategy model.
The cloud computing unit runs on the cloud server and is used for storing and processing crop growth process data and building an agricultural greenhouse control strategy model based on deep learning and expert knowledge.
The cloud computing unit includes: the system comprises a remote data storage module, a remote data analysis module, a remote control strategy management module and a remote control strategy operation module.
Further, the remote data storage module is used for receiving and storing the crop growth process data acquired by the local data storage module for a long time, wherein the crop growth process data include the crop growth process data and the crop growth process historical data in the current period of time, and the data characteristic information extracted by the local data preprocessing module provides sufficient data support for model construction, and the data can be remotely inquired.
Specifically, the remote query supports a computer end web, a mobile end app, a WeChat applet and a public number.
Further, the remote data storage module further comprises an expert knowledge base.
Preferably, the expert knowledge base divides the growth environment of the corresponding period into four growth areas which are very suitable, relatively suitable and unsuitable according to the growth and development period of the crops, generally comprising four periods of a germination period, a seedling period, a shoot-throwing and rooting period and a fruiting period, and then provides data interval values of the growth process of the corresponding crops in the different growth areas.
Further, the remote data analysis module is used for training the agricultural greenhouse control strategy model by using the data stored by the remote data storage module.
Preferably, the method for training the agricultural greenhouse control strategy model is shown in fig. 2, and the specific process comprises the following 4 steps.
Step 1: and marking the pretreated crop growth process data by means of expert knowledge. The crop growth process data comprises: soil pH value, soil EC value, CO2 concentration value, soil humiture, light intensity, air humiture, insect pest and disease. The label represents the growth environment state of the crops, and is a combination of the types of the crops, the growth and development periods of the crops and the growth environment areas, such as the germination period of blueberries, is suitable.
Specifically, the crop types comprise strawberries and blueberries; the crop growth and development period comprises a germination period, a seedling period, a leaf throwing and seedling growing period and a fruiting period; the growth environment area includes very suitable, more suitable and unsuitable.
Step 2: and dividing the marked crop growth process data into data sets by adopting a training, verifying and testing trisection method, and inputting the established deep neural network model for learning and testing to obtain the trained deep neural network model.
Specifically, the deep neural network model comprises an input layer, a multi-layer LSTM network, a full connection layer and an output layer which are sequentially arranged, wherein the full connection layer executes classification, and random inactivation operation is carried out on nodes of the full connection layer by applying a ReLU function.
And step 3: and respectively inputting the marked crop growth process data into an expert knowledge base and the trained deep neural network model, and then fusing respective judgment results through a multi-mode fusion network to obtain an agricultural greenhouse control strategy model.
Specifically, the multi-mode fusion network adopts 1-2 layers of fully-connected networks, and weights are given to the discrimination results of the models, so that the crop growth environment state corresponding to the current crop growth process data is given.
And 4, step 4: the method comprises the steps of preprocessing current crop growth process data, inputting the preprocessed current crop growth process data into an agricultural greenhouse control strategy model, giving a crop growth environment state, giving a bottom layer equipment parameter adjusting result according to a preset control strategy and suggestions provided by the agricultural greenhouse control strategy model, sending the bottom layer equipment parameter adjusting result to a corresponding PLC (programmable logic controller) device for execution, judging a control effect according to error magnitude through continuous comparison of output and input, adjusting a control algorithm in the PLC device, optimizing the control strategy, and achieving self-learning, adjustment and evolution of the control algorithm.
Specifically, when the opinion provided by the agricultural greenhouse control strategy model may have the same index of operation optimization, multiple adjustment strategies of the parameters of the bottom layer equipment are given, at this time, the remote control strategy operation module evaluates the strategies according to the actual index set values of the historical bottom layer equipment, and the strategy with the minimum evaluation result is sent to the local control strategy operation module.
Further, the remote control strategy management module is used for updating and controlling the agricultural greenhouse control strategy model, and receiving and processing the agricultural greenhouse control strategy model from the local control strategy management module, the data preprocessing rule and the feature extraction rule request.
Preferably, the agricultural greenhouse control strategy model is updated and controlled according to whether the agricultural greenhouse control strategy model is trained by adopting the crop growth process data in the current period of time after being preprocessed in the remote data storage module. And if so, updating the agricultural greenhouse control strategy model.
Further, the remote control strategy operation module is configured to preset a control strategy, and evaluate and issue multiple adjustment strategies that may exist in the bottom layer device parameter.
Specifically, the preset control strategy includes step length adjustment, remote/local control, and stop conditions. The stop condition is that the output and input errors are less than some given threshold. And if the remote/local control is remote control, adjusting the parameters of the bottom layer equipment by the remote control strategy operation module.
And the data transmission unit is used for transmitting data through a public network or a private line, and the transmission mode comprises 4G, 5G, Wi-Fi and an Internet of things gateway.
The invention discloses an agricultural greenhouse control device based on cloud-edge cooperation, which comprises a data acquisition unit, a data transmission unit, an edge computing unit and a cloud computing unit; the data acquisition unit is used for acquiring growth process data of agricultural greenhouse crops; the data transmission unit is used for sending the crop growth process data collected by the data collection unit to the edge calculation unit; the edge calculation unit is arranged on the local control computer and used for receiving the crop growth process data sent by the data transmission unit, generating a log file of the crop growth process according to the crop growth process data and simultaneously carrying out local control on the agricultural greenhouse; the cloud computing unit runs on the cloud server and is used for storing and processing crop growth process data and building an agricultural greenhouse control strategy model based on deep learning and expert knowledge.
(1) Real-time monitoring and intelligent control of bottom equipment of the agricultural greenhouse are realized by utilizing a cloud edge cooperative framework; through continuous innovation of three aspects of crop visual image acquisition, crop growth process data integral analysis and edge control, the agricultural greenhouse management personnel can be helped to collect and manage abundant data, and the flexibility of agricultural greenhouse management is realized.
(2) By adopting a data processing mode combining real-time response of the edge computing unit and deep analysis of the cloud computing unit, on one hand, the PLC device which can be correspondingly installed and connected in the environment of the edge computing unit in real time can send data and process the sent data in time, and the delay is almost zero, on the other hand, the cloud computing unit collects the data and then conducts deep analysis and edge computing, so as to guide the edge computing to correctly respond to the PLC device to control bottom equipment. Meanwhile, the uploading time of mass data is shortened, network resources are saved, the problems of insufficient data correlation analysis and insufficient sharing in the crop growth process are solved, the storage cost on the cloud can be obviously reduced, and effective data management is facilitated.
According to the agricultural greenhouse control device based on cloud-edge cooperation, the cloud computing unit carries out deep analysis after collecting data of the edge computing unit and feeds back the data to the edge computing unit, and the agricultural greenhouse control device has the technical advantages that the problems of insufficient correlation analysis and insufficient sharing of crop growth process data can be solved, crop growth environment and state information can be comprehensively given, efficient and accurate intelligent remote management of an agricultural greenhouse is achieved, and the like.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (10)
1. An agricultural greenhouse control device based on cloud edge coordination is characterized by comprising a data acquisition unit, a data transmission unit, an edge computing unit and a cloud computing unit;
the data acquisition unit is used for acquiring growth process data of agricultural greenhouse crops;
the data transmission unit is used for sending the crop growth process data collected by the data collection unit to the edge calculation unit;
the edge calculation unit is arranged on the local control computer and used for receiving the crop growth process data sent by the data transmission unit, generating a log file of the crop growth process according to the crop growth process data and simultaneously carrying out local control on the agricultural greenhouse;
the cloud computing unit runs on the cloud server and is used for storing and processing crop growth process data and building an agricultural greenhouse control strategy model based on deep learning and expert knowledge.
2. The agricultural greenhouse control device based on cloud-edge coordination as claimed in claim 1, wherein the edge computing unit comprises a local data storage module, a local data preprocessing module, a local control policy management module, a local control policy operation module and a local early warning management module.
3. The agricultural greenhouse control device based on cloud-edge coordination as claimed in claim 1, wherein the cloud computing unit comprises a remote data storage module, a remote data analysis module, a remote control strategy management module and a remote control strategy operation module.
4. The cloud-edge-based collaborative agricultural greenhouse control device of claim 1, wherein the crop growth process data includes soil PH, soil EC, CO2 concentration, soil temperature and humidity, light intensity, air temperature and humidity, pest data, and disease data.
5. The cloud-edge-based cooperative agricultural greenhouse control device as claimed in claim 4, wherein the pest data and disease data comprise crop video data and crop image data collected by a camera device, and the crop video data and the crop image data are processed through a deep learning algorithm to perform growth period identification and pest identification on crops.
6. The cloud-edge-collaboration-based agricultural greenhouse control device as claimed in claim 2, wherein the local data storage module is used for storing crop growth process data in a current period of time and uploading the data to the cloud computing unit when a task is idle.
7. The agricultural greenhouse control device based on cloud edge coordination as claimed in claim 2, wherein the local data preprocessing module is configured to perform uniform alignment of timestamps and data preprocessing on the crop growth process data in the local data storage module, and transmit the preprocessed extracted data features to the cloud computing unit through the data transmission unit.
8. The cloud-edge-collaboration-based agricultural greenhouse control device as claimed in claim 2, wherein the local control strategy management module is configured to request a newly trained agricultural greenhouse control strategy model and the data preprocessing rule and the feature extraction rule from a cloud computing unit.
9. The cloud-edge-collaboration-based agricultural greenhouse control device as claimed in claim 3, wherein the remote data analysis module is used for training an agricultural greenhouse control strategy model by using data stored in the remote data storage module.
10. The cloud-edge-based collaborative agricultural greenhouse control device according to claim 3, wherein the remote control policy management module is configured to update and control an agricultural greenhouse control policy model, and receive and process the agricultural greenhouse control policy model and the data preprocessing rule and feature extraction rule requests from the local control policy management module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011275023.5A CN112465109A (en) | 2020-11-16 | 2020-11-16 | Green house controlling means based on cloud limit is in coordination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011275023.5A CN112465109A (en) | 2020-11-16 | 2020-11-16 | Green house controlling means based on cloud limit is in coordination |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112465109A true CN112465109A (en) | 2021-03-09 |
Family
ID=74836216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011275023.5A Pending CN112465109A (en) | 2020-11-16 | 2020-11-16 | Green house controlling means based on cloud limit is in coordination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465109A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113093835A (en) * | 2021-04-13 | 2021-07-09 | 广州中国科学院沈阳自动化研究所分所 | Greenhouse control system and method based on edge controller |
| CN114097563A (en) * | 2021-12-06 | 2022-03-01 | 湖南省烟草公司衡阳市公司常宁市分公司 | Simple tobacco seedling raising greenhouse management method |
| CN114726889A (en) * | 2022-03-09 | 2022-07-08 | 昆明理工大学 | Intelligent planting method and system based on end-edge-cloud cooperation |
| CN114911174A (en) * | 2022-02-09 | 2022-08-16 | 北大荒信息有限公司 | Plant bionic method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108901474A (en) * | 2018-05-03 | 2018-11-30 | 河北师范大学 | A kind of intelligence planting greenhouse and control method |
| CN111766820A (en) * | 2020-07-20 | 2020-10-13 | 成都快乐猴科技有限公司 | Intelligent fine management control system applied to intelligent agriculture |
| CN111818146A (en) * | 2020-07-01 | 2020-10-23 | 深圳市中深农创科技有限公司 | SOA cloud computing intelligent agricultural data processing method and system |
-
2020
- 2020-11-16 CN CN202011275023.5A patent/CN112465109A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108901474A (en) * | 2018-05-03 | 2018-11-30 | 河北师范大学 | A kind of intelligence planting greenhouse and control method |
| CN111818146A (en) * | 2020-07-01 | 2020-10-23 | 深圳市中深农创科技有限公司 | SOA cloud computing intelligent agricultural data processing method and system |
| CN111766820A (en) * | 2020-07-20 | 2020-10-13 | 成都快乐猴科技有限公司 | Intelligent fine management control system applied to intelligent agriculture |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113093835A (en) * | 2021-04-13 | 2021-07-09 | 广州中国科学院沈阳自动化研究所分所 | Greenhouse control system and method based on edge controller |
| CN114097563A (en) * | 2021-12-06 | 2022-03-01 | 湖南省烟草公司衡阳市公司常宁市分公司 | Simple tobacco seedling raising greenhouse management method |
| CN114911174A (en) * | 2022-02-09 | 2022-08-16 | 北大荒信息有限公司 | Plant bionic method and device |
| CN114726889A (en) * | 2022-03-09 | 2022-07-08 | 昆明理工大学 | Intelligent planting method and system based on end-edge-cloud cooperation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN209517198U (en) | A kind of wisdom agricultural standardization management system | |
| CN112465109A (en) | Green house controlling means based on cloud limit is in coordination | |
| KR101852987B1 (en) | Module type plants factory system for cultivating mushroom | |
| CN111476149A (en) | Plant cultivation control method and system | |
| CN111504371A (en) | Big data service system | |
| CN105843147A (en) | Smart agriculture monitoring and management system | |
| CN114442705B (en) | Intelligent agricultural system based on Internet of things and control method | |
| KR20220071405A (en) | Agricultural support system and method using big data of smart farm | |
| Zhou et al. | Applications of Internet of Things in the facility agriculture | |
| Carlos et al. | Monitoring system of environmental variables for a strawberry crop using IoT tools | |
| CN117036088A (en) | Data acquisition and analysis method for identifying growth situation of greening plants by AI | |
| CN113273449A (en) | Digital twin body construction method for precise monitoring of sunlight greenhouse | |
| CN115993148A (en) | Warmhouse booth monitored control system based on edge calculation | |
| AU2021105327A4 (en) | A computer implemented and IoT based method for increasing crop production using machine learning model | |
| CN117893346A (en) | AI intelligent agriculture harvesting management system based on Internet of things and application thereof | |
| Singla et al. | IoT based monitoring for the growth of basil using machine learning | |
| CN114543869A (en) | Agricultural braced system based on internet of things | |
| CN109631990B (en) | Agricultural information acquisition system based on big data and WSN technology | |
| CN112581302A (en) | Agricultural thing allies oneself with management monitoring system | |
| KR20220036433A (en) | Fruit growth monitoring system and fruit growth monitoring method thereof | |
| CN112130608A (en) | Wisdom big-arch shelter system | |
| CN110308710A (en) | A kind of tomato planting monitor supervision platform | |
| CN115756037A (en) | Greenhouse vegetable management and control method and system | |
| CN211908856U (en) | Plant data acquisition system based on Internet of things | |
| Osupile et al. | A Review on Agriculture Monitoring Systems using Internet of Things (IoT) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |